Celebrate your peers with the Postgrad Awards NOMINATE NOW
University of Hong Kong Featured PhD Programmes
University of Hull Featured PhD Programmes

Machine Learning and Expert based system for soft fruit yield forecasting


Department of Computing Science

, Mr Jan Redpath Thursday, April 15, 2021 Funded PhD Project (European/UK Students Only)
Aberdeen United Kingdom Machine Learning Computer Science Software Engineering

About the Project

We are looking for a highly motivated student to work on a 3-year fully funded interdisciplinary PhD project on Machine/Deep Learning and Expert based system for soft fruit yield forecasting.

The project is a collaboration between the University of Aberdeen’s Department of Computing Science and Angus Soft Fruits Ltd (industry partner), and is supported by The Data Lab.

The position will be based in the Department of Computing Science, University of Aberdeen, but close collaboration with Angus Soft Fruits Ltd and farmers across Scotland is expected.

University of Aberdeen, established in 1495, is one of the oldest Universities in the UK and ranks among the top 200 Universities in the world (THE 2020).

According to the National Farmers Union (NFU - https://www.nfus.org.uk/farming-facts.aspx), some 80% of Scotland’s land mass is under agricultural production, highlighting the importance of farming for the Nation’s economy. The overall turnover across farmers, crofters and growers is estimated at £2.9 billion a year and contribute to Scotland’s £5 billion food drink exports. In soft fruit industry alone, it is estimated that approximately 2,100 hectares are used for growing soft fruits, leading to an annual production of more than 2,900 tonnes of raspberries and 25,000 tonnes of strawberries.

Deep Learning theory/applications have seen an immense development in the past few years across a number of areas, such as convolutional and Capsule Neural Networks [1,2], Generative Adversarial Networks, Bayesian Deep Learning [3], etc. However, some open problems, such as improving performance whilst reducing model complexity, learning with few examples, neurosymbolic AI, etc., are some areas that further investigations are needed to move onto the next phase of deep/machine learning research that can inform novel and impactful applications (e.g. those with limited availability of data).

This project aims at developing and applying novel machine learning techniques for developing a system that can accurately predict/forecast strawberry yield [4,5]. Through our collaboration with Angus Soft Fruits Ltd and farmers across Scotland, the project will benefit from large amounts of data.

Areas of investigation might involve (but not limited to) data augmentation with generative models, causal inference, uncertainty estimation, time-series and tabular data analysis with deep learning techniques, intra-field yield variation, etc.

As with every PhD project, there is scope to shape the exact theoretical focus within Machine Learning so that a more accurate and robust yield forecasting system can be developed.

The student will work closely with other Researchers/PhD students within Dr Leontidis’s lab/Department and will have access to HPC/GPU facilities, and also funding for training/conferences. In addition, the student will further benefit from participating in activities and events organised by the Data Lab.

For any information or informal discussion please contact Dr Georgios Leontidis, Interim Director for AI and Data & Associate Professor (SL) in Machine Learning .

The successful applicant will be expected to contribute to all stages of the project from experimental design, through to conducting experiments and collecting, processing and interpreting the data before writing everything up.

Selection will be made on the basis of academic merit. The successful candidate should have, or expect to obtain, a UK Honours degree at 2.1 or above (or equivalent) in Computer Science, Engineering or Mathematics. Highly Desirable: MSc in Machine Learning, AI, Data Science, or similar.

Essential background and Knowledge: Strong skills in linear algebra, mathematics, programming (advanced Python), machine learning principles, problem solving.

Knowledge of: Machine Learning, Deep Learning, Artificial Intelligence, Knowledge Representation, Time Series Analysis, programming in Python, and Software & User Interface Development.

APPLICATION PROCEDURE:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php

- Apply for the Degree of Doctor of Philosophy in Computing Science

- State the name of the lead supervisor as the Name of Proposed Supervisor

- State the exact project title on the application form

- All Degree Certificates/Academic Transcripts (officially translated into English and original)

- 2 Academic References on official headed paper and signed or sent from referees official email address

- Detailed CV

We reserve the right to close the advert earlier should a suitable candidate be found before the advertised closing date.


Funding Notes

Tuition fees will be paid at UK/EU rates for 2020/2021academic session (£4,407)along with a maintenance stipend of £15,285, paid monthly in arrears. Due to funding criteria we cannot accept applications from non UK/EU nationals. EU nationals are required to commence study by 1 July 2021.

References

1. De Sousa Ribeiro, Fabio, Georgios Leontidis, and Stefanos Kollias. "Introducing routing uncertainty in capsule networks." Advances in Neural Information Processing Systems 33 (2020).
2. De Sousa Ribeiro, Fabio, Georgios Leontidis, and Stefanos Kollias. "Capsule Routing via Variational Bayes." AAAI, (2020).
3. Ribeiro, Fabio De Sousa, Francesco Calivá, Mark Swainson, Kjartan Gudmundsson, Georgios Leontidis, and Stefanos Kollias. "Deep Bayesian Self-Training." Neural Computing and Applications (2019).
4. Alhnaity, Bashar, Stefanos Kollias, Georgios Leontidis, Shouyong Jiang, Bert Schamp, and Simon Pearson. "An autoencoder wavelet based deep neural network with attention mechanism for multistep prediction of plant growth." Information Sciences” (2020).
5. Alhnaity, Bashar, Simon Pearson, Georgios Leontidis, and Stefanos Kollias. "Using deep learning to predict plant growth and yield in greenhouse environments." In International Symposium on Advanced Technologies and Management for Innovative Greenhouses: GreenSys2019 1296, (2020).

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here

The information you submit to Aberdeen University will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.

* required field

Your enquiry has been emailed successfully



Search Suggestions

Search Suggestions

Based on your current searches we recommend the following search filters.



FindAPhD. Copyright 2005-2021
All rights reserved.